← notes

research · NYU WIRELESS

Spatial Intelligence

Runtime object association when the camera moves — and when the pose you trusted is wrong.

Context NYU WIRELESS Evaluation 2,400 train / 186 val / 771 test Code private

Problem framing

Keep object identity and association coherent as viewpoint changes. Clean pose is the easy case. Injected pose noise is the honest case. I treat them as separate evaluation stories so a single headline number cannot hide a brittle pipeline.

Results

strict-threshold F1 0.598 clean pose
strict-threshold F1 0.484 injected pose noise

Coverage and pseudo-label quality are reported separately. A system can look strong on matched cases while quietly skipping hard ones, or while training on labels that are not as clean as the paper title implies.

Methodology

Code visibility

The implementation repository is private. Model weights, dataset dumps, training configs, and the private repo are not published. This page describes the research question and the standard of evidence — enough to start a conversation.